A Model-Class Comparison of Large Language Models for Translating Chinese Route Instructions into Robot Command Sequences

Advances in large language models (LLMs) have accelerated the real-world deployment of embodied intelligent robots, supporting intuitive human–robot interaction without specialized robotics expertise. However, few systematic assessments examine how well LLMs translate natural-language route instructions into executable robot command sequences, particularly for non-English instructions and across deployment-relevant model classes. In this paper, a Chinese route-instruction corpus was constructed, which comprised 212 instructions collected from six native speakers across 50 procedurally generated town maps. Each was annotated with a ground-truth command sequence verified by simulation to reach its goal, and a 100% performance ceiling was established. Using this corpus, 12 LLMs spanning three capability tiers—cloud proprietary models, mid-sized open-weight models, and small open-weight models—were evaluated under three system prompts differing only in the number of worked examples (zero, one, and three). Open-weight models in the 3–9B range reached at most 9.2% of goals, while proprietary cloud models reached 80.0%, a substantial gap that increasing the number of worked examples did not measurably narrow. A paired analysis across the three prompt conditions detected no reliable effect of demonstration count: pooled path_reach rose modestly from 25.0% under zero-shot prompting to 27.2% with one example and 27.7% with three examples (three versus zero examples: odds ratio: 1.15; 95% CI: 0.98–1.34). None of these differences was significant after multiple-comparison correction (Holm-adjusted p ≥ 0.247). Low-Rank Adaptation (LoRA) fine-tuning on 126 examples raised mid-sized open-weight models to 27.7–35.4%, and the gain spanned both output-format compliance and route competence.

Authors

Institutions

Publication Details

Journal
Journal of Sensor and Actuator Networks
Published
2026-11-17
DOI
https://doi.org/10.3390/jsan15060091
Primary Topic
Speech and dialogue systems
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

A Model-Class Comparison of Large Language Models for Translating Chinese Route Instructions into Robot Command Sequences

Ruizhe Yang, Yuki Nishimura
Journal of Sensor and Actuator Networks
Speech and dialogue systems
article

A Model-Class Comparison of Large Language Models for Translating Chinese Route Instructions into Robot Command Sequences

Ruizhe Yang, Yuki Nishimura
article en

Abstract

Advances in large language models (LLMs) have accelerated the real-world deployment of embodied intelligent robots, supporting intuitive human–robot interaction without specialized robotics expertise. However, few systematic assessments examine how well LLMs translate natural-language route instructions into executable robot command sequences, particularly for non-English instructions and across deployment-relevant model classes. In this paper, a Chinese route-instruction corpus was constructed, which comprised 212 instructions collected from six native speakers across 50 procedurally generated town maps. Each was annotated with a ground-truth command sequence verified by simulation to reach its goal, and a 100% performance ceiling was established. Using this corpus, 12 LLMs spanning three capability tiers—cloud proprietary models, mid-sized open-weight models, and small open-weight models—were evaluated under three system prompts differing only in the number of worked examples (zero, one, and three). Open-weight models in the 3–9B range reached at most 9.2% of goals, while proprietary cloud models reached 80.0%, a substantial gap that increasing the number of worked examples did not measurably narrow. A paired analysis across the three prompt conditions detected no reliable effect of demonstration count: pooled path_reach rose modestly from 25.0% under zero-shot prompting to 27.2% with one example and 27.7% with three examples (three versus zero examples: odds ratio: 1.15; 95% CI: 0.98–1.34). None of these differences was significant after multiple-comparison correction (Holm-adjusted p ≥ 0.247). Low-Rank Adaptation (LoRA) fine-tuning on 126 examples raised mid-sized open-weight models to 27.7–35.4%, and the gain spanned both output-format compliance and route competence.

Journal of Sensor and Actuator NetworksVol. 15(6)
Hangzhou Dianzi University (CN)
Speech and dialogue systems
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon